react-router: Skill for Codex

.agents/skills/prepare-release-notes/SKILL.md

prepare-release-notes is a skill for Codex from remix-run/react-router. It costs 86 tokens per session (959 once invoked), scanned A, original, MIT.

A guide for polishing pending change files, which describe updates that will appear in a software release, for the React Router project.

In plain words
What is it for?
Use it to inspect and normalize pending change files, rewrite release bullets, and decide when a manual release note is needed.
Why use it?
It keeps release notes consistent and prevents generated release text from containing commit labels, awkward verb forms, or unnecessary manual notes.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is remix-run/react-router's own configuration. It tells Codex how to work on react-router itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything react-router configures →

About the project

React Router is a routing system for React applications that maps URLs to the interface shown on screen. Developers use it either as a small library within their own application structure or as part of a full React framework.

remix-run/react-router · 56,622 stars · on GitHub · reactrouter.com

Reuse

Borrowing it

Nothing to install: this file belongs to remix-run/react-router. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/remix-run/react-router/main/.agents/skills/prepare-release-notes/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/remix-run/react-router

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prepare-release-notes

README.md
[![agentmods](https://agentmods.dev/badge/skills/remix-run/react-router/prepare-release-notes/github.svg)](https://agentmods.dev/skills/remix-run/react-router/prepare-release-notes)
Your own site
<a href="https://agentmods.dev/skills/remix-run/react-router/prepare-release-notes"><img src="https://agentmods.dev/badge/skills/remix-run/react-router/prepare-release-notes/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prepare-release-notes

Your own site · 80×15
<a href="https://agentmods.dev/skills/remix-run/react-router/prepare-release-notes"><img src="https://agentmods.dev/badge/skills/remix-run/react-router/prepare-release-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 959 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Snyk pass 7 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00086 $0.00959
Opus 5.5 $0.00034 $0.00384
Sonnet 5.5 $0.00017 $0.00192
Haiku 4.5 $0.00009 $0.00096

Measured 1mo ago against content hash c2476870304a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prepare-release-notes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/prepare-release-notes/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prepare Release Notes

Polish pending React Router change files and add manual release notes only when the release needs narrative context beyond the generated change lists.

Workflow

  1. Inspect local state:
git status --short
find packages -path '*/.changes/*.md' -not -name README.md -not -name .gitkeep -print | sort
  1. Read every pending change file. Do not edit generated changelogs or released notes directly.

  2. Normalize each change file:

    • Remove feat:, feat(...), fix:, and fix(...) semantic-commit prefixes from prose
    • Use present or imperative tense for the first line and top-level release bullets: prefer Add, Fix, Remove, Support, Stabilize, Preserve, Update, Avoid, Prevent, Throw, Warn, Expose
    • Nested detail bullets can stay explanatory when they expand on the parent bullet; do not rewrite them solely to force present or imperative tense
    • Remove terminal sentence periods from bullet items because release generation appends PR/commit links after the first bullet line
    • Remove terminal sentence periods from nested bullet items too, unless the punctuation is part of code, a URL, an abbreviation, a version number, or another token where removing it would be wrong
    • If one bullet contains multiple sentences, split it into a shorter parent bullet plus nested bullet items
    • Keep the first line concise and user-facing; use nested bullets for details or migration notes
  3. Review whether scripts/changes/whats-changed.md is needed:

    • Read CHANGELOG.md examples or references/whats-changed.md when uncertain
    • Add scripts/changes/whats-changed.md only for features, future flag stabilizations, unstable flags, migration guidance, breaking bug fixes, or complex behavior that needs long-form text or examples
    • Do not add it for ordinary bug fixes, dependency cleanup, internal refactors, or release bullets that are already clear
    • If adding it, write the body only; the release script adds ### What's Changed when missing

Read the full file on GitHub · 99 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 99 lines · 86 tokens per session scan A c2476870304a

Subscribe to this mod's changes

prepare-release-notes is a skill published in the GitHub repository remix-run/react-router (56,622 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 959 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.